|
PureBytes Links
Trading Reference Links
|
Hello all,
Since we have been throwing around methods of optimizing and selecting objective measures, I was wondering if some of the more skilled in our group could translate the following passage, as my Sergeant would say back in my Army days " in terms a 10-year old could understand". The passage is from from Bob Pelletier in the latest CSI Technical Journal.
Some pre-emptive questions belfore the passage:
1. Fred, is Pelletier's comments the same as what you are referring to in terms of making system adjustments on the fly? Optimizing on only OS data on a go-forward basis? If you are willing to break it down into a process it would be much appreciated by myself and probably a lot of others.
2. If he is going only one pass through the data how is he coming up with paramaters?
I'm typing out his comments so please forgive typos.
PELLETIER'S COMMENTS
OCT 03 CSI TECHNICAL JOURNAL
"... This is a novel approach that depends upon large amounts of data to arrive at a solution. Theoretically, the more data supplied the better should be the result. It views all markets and variables forward in time. There is no hindsight optimization testing. Analysts correctly believe that basing future decisions on results optimized in the past tends to produce unrepeatable performance in real-time trading. Such complaints boil down to the derogatory label of "curve fitting". None of that is done here. This model learns by studying only future (or forward) facts in time. Only one pass through all of the supplied data defines the trading model that will be forecasting tomorrow's prices.
The model-building stage of the process includes a feedback mechanism that measures the daily causal effects of each independent variable upon the movement of the dependent variable. The feedback logic tends to emphasize the positive and negative effects of each variable upon the dependent variable. The decision-making process process therefore becomes increasingly heuristic over time as more and more price history is reviewed. The model is encouraged by predictive success and discouraged by the apparent failures of all independent time series supplied. The basic intent of the process is to teach the computer to profitably trade a dependent variable basded upon the predictive characteristics of all independent variables...."
COMMENTS???
Do you Yahoo!?
The New Yahoo! Shopping - with improved product search
Yahoo! Groups Sponsor
ADVERTISEMENT
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|